ableton-mcp

Overview Schema Source Related Servers Discussions Admin

get_scene_launch_context

Read-onlyIdempotent

Preview a Session scene before launch, returning every track/slot action, clip/stop/group status, arm and recording risks, playback state, and musical context without changing selection.

Instructions

Preview an exact Session scene in one native read: every track/slot, clip/stop/Group actions, arms, recording risks, current playback and global/scene musical context. Preserves selection and playback. Launch metadata only; no audible or follow-action prediction. All profile.

Input Schema

Name	Required	Description	Default
`sceneId`	Yes	ID from list_scenes.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.1Oct 23, 2026

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / anyOf

Added value: +[
+  {
+    "properties": {
+      "clipId": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "deviceId": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "identityToken": {
+        "type": "string"
+      },
+      "reason": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "sceneId": {
+        "type": "string"
+      },
+      "scenes": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "setFingerprint": {
+        "type": "string"
+      },
+      "stateVersion": {
+        "minimum": 1,
+        "type": "integer"
+      },
+      "status": {
+        "type": "string"
+      },
+      "supported": {
+        "type": "boolean"
+      },
+      "trackId": {
+        "type": "string"
+      },
+      "tracks": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "transport": {
+        "type": "object"
+      }
+    },
+    "required": [
+      "stateVersion"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "error": {
+        "properties": {
+          "message": {
+            "type": "string"
+          },
+          "outcome": {
+            "enum": [
+              "unknown",
+              "not_executed"
+            ]
+          }
+        },
+        "required": [
+          "message",
+          "outcome"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

Addedv0.3.0Oct 19, 2026

TDQS

A3.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive. The description adds value beyond them by stating the operation 'Preserves selection and playback' (a side-effect guarantee the annotations do not express) and by scoping the result to launch metadata with no audible or follow-action prediction. 'All profile' is left unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core verb and compact at two sentences, but the token-dense enumeration and the cryptic fragment 'All profile' cost clarity. Some listed items (arms, recording risks, playback) could be compressed into a cleaner phrase.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not detail return values, and it still sketches the returned content well enough to set expectations. The unexplained 'All profile' scope marker and absent preconditions (e.g., session must be open) are the main residual gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter with 100% schema description coverage ('ID from list_scenes.'), so the schema carries the meaning. The description adds nothing about sceneId format or sourcing, making the 3 baseline appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb and resource: 'Preview an exact Session scene in one native read', followed by an enumeration of what the read covers (tracks/slots, clip/stop/Group actions, arms, recording risks, playback, musical context). It is clearly a preview/read, distinguishable from the sibling launch_scene which actually launches. Dense jargon ('Group actions', 'All profile') slightly dulls precision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: that this is a pre-launch preview, and the negative boundary 'Launch metadata only; no audible or follow-action prediction' tells the agent what it will not get. No sibling is named and no explicit 'use this before launch_scene' routing is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server